© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 15697
    Prev
    Next
    INDEX
    Explanations

    photo captions with author credits

    oai_token-act-pair · gpt-3.5-turbo

    instances of photo credits and captions in context to news articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĹ¼
    -0.74
     Danish
    -0.72
     Copenhagen
    -0.70
    uador
    -0.70
    anmar
    -0.68
     Chilean
    -0.68
     Bale
    -0.67
     Icelandic
    -0.66
     Nicaragua
    -0.66
    ourt
    -0.66
    POSITIVE LOGITS
    CLOSE
    1.30
    âĸº
    1.10
    Read
    1.04
    Buy
    1.04
    SHARE
    0.83
     VIDEOS
    0.80
    hello
    0.77
    Contribut
    0.77
    Correct
    0.75
     FIX
    0.73
    Activations Density 0.077%

    No Known Activations